Improved Neural Network Algorithm Based Flow Characteristic Curve Fitting for Hydraulic Turbines

Hong Pan, Chenyang Hang (), Fang Feng, Yuan Zheng and Fang Li
Additional contact information
Hong Pan: College of Energy and Electrical Engineering, Hohai University, Nanjing 211100, China
Chenyang Hang: College of Energy and Electrical Engineering, Hohai University, Nanjing 211100, China
Fang Feng: College of Energy and Electrical Engineering, Hohai University, Nanjing 211100, China
Yuan Zheng: College of Energy and Electrical Engineering, Hohai University, Nanjing 211100, China
Fang Li: College of Energy and Electrical Engineering, Hohai University, Nanjing 211100, China

Sustainability, 2022, vol. 14, issue 17, 1-15

Abstract: One of the most important characteristic curves in the economic operation of hydropower plants is the turbine flow characteristic curve, which illustrates the law of fluctuation between the characteristic parameters of the turbine under various operating situations. This article proposes an IPSO-LSTM-based refinement method for fitting the turbine flow characteristic curve using deep learning methods, and verifies the effectiveness of the method by comparison to solve the problem that traditional mathematical fitting methods are difficult to meet the requirements of today’s many complex working conditions. Firstly, a deep LSTM network model is established based on the input and output quantities, and then the IPSO method is used to find the optimum number of neurons, the learning rate and the maximum number of iterations of the LSTM units in the network model and other key parameters to determine the relevant training parameters. The results show that the model can effectively improve the accuracy of fitting and predicting the turbine flow characteristics, which is of great significance to the study of the economic operation of hydropower plants and the non-linear characteristics of the turbine.

Keywords: LSTM; hydraulic turbines; flow characteristic curves; deep learning; IPSO (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/14/17/10757/pdf (application/pdf)
https://www.mdpi.com/2071-1050/14/17/10757/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:14:y:2022:i:17:p:10757-:d:900775

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().